Universal Approximation of Visual Autoregressive Transformers

• URL: http://arxiv.org/abs/2502.06167v1
• Date: Mon, 10 Feb 2025 05:36:30 GMT
• Title: Universal Approximation of Visual Autoregressive Transformers
• Authors: Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song,
• Abstract summary: We extend our analysis to include Visual Autoregressive transformers. Var represents a big step toward generating images using a novel, scalable, coarse-to-fine next-scale prediction'' framework. Our results provide important design principles for effective and computationally efficient VAR Transformer strategies.
• Score: 28.909655919558706
• License:
• Abstract: We investigate the fundamental limits of transformer-based foundation models, extending our analysis to include Visual Autoregressive (VAR) transformers. VAR represents a big step toward generating images using a novel, scalable, coarse-to-fine ``next-scale prediction'' framework. These models set a new quality bar, outperforming all previous methods, including Diffusion Transformers, while having state-of-the-art performance for image synthesis tasks. Our primary contributions establish that, for single-head VAR transformers with a single self-attention layer and single interpolation layer, the VAR Transformer is universal. From the statistical perspective, we prove that such simple VAR transformers are universal approximators for any image-to-image Lipschitz functions. Furthermore, we demonstrate that flow-based autoregressive transformers inherit similar approximation capabilities. Our results provide important design principles for effective and computationally efficient VAR Transformer strategies that can be used to extend their utility to more sophisticated VAR models in image generation and other related areas.

Related papers

• Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolution [6.367865391518726]
  Transformer-based models have achieved remarkable results in low-level vision tasks including image super-resolution (SR) To activate more input pixels globally, hybrid attention models have been proposed. We employ wavelet losses to train Transformer models to improve quantitative and subjective performance.
  arXiv  Detail & Related papers  (2024-04-17T11:25:19Z)
• HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling [126.89573619301953]
  We propose a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) HiViT enjoys both high efficiency and good performance in MIM. In running MAE on ImageNet-1K, HiViT-B reports a +0.6% accuracy gain over ViT-B and a 1.9$times$ speed-up over Swin-B.
  arXiv  Detail & Related papers  (2022-05-30T09:34:44Z)
• Your Transformer May Not be as Powerful as You Expect [88.11364619182773]
  We mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. We present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. We develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions.
  arXiv  Detail & Related papers  (2022-05-26T14:51:30Z)
• Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks [126.33843752332139]
  We introduce Group-wise Transformation towards a universal yet lightweight Transformer for vision-and-language tasks, termed as LW-Transformer. We apply LW-Transformer to a set of Transformer-based networks, and quantitatively measure them on three vision-and-language tasks and six benchmark datasets. Experimental results show that while saving a large number of parameters and computations, LW-Transformer achieves very competitive performance against the original Transformer networks for vision-and-language tasks.
  arXiv  Detail & Related papers  (2022-04-16T11:30:26Z)
• Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations [61.95114821573875]
  We introduce Plug-In Inversion, which relies on a simple set of augmentations and does not require excessive hyper- parameter tuning. We illustrate the practicality of our approach by inverting Vision Transformers (ViTs) and Multi-Layer Perceptrons (MLPs) trained on the ImageNet dataset.
  arXiv  Detail & Related papers  (2022-01-31T02:12:45Z)
• Towards End-to-End Image Compression and Analysis with Transformers [99.50111380056043]
  We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. We aim to redesign the Vision Transformer (ViT) model to perform image classification from the compressed features and facilitate image compression with the long-term information from the Transformer. Experimental results demonstrate the effectiveness of the proposed model in both the image compression and the classification tasks.
  arXiv  Detail & Related papers  (2021-12-17T03:28:14Z)
• PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion [37.993611194758195]
  We propose a Patch PyramidTransformer(PPT) to address the issues of extracting semantic information from an image. The experimental results demonstrate its superior performance against the state-of-the-art fusion approaches.
  arXiv  Detail & Related papers  (2021-07-29T13:57:45Z)
• Transformer-Based Deep Image Matching for Generalizable Person Re-identification [114.56752624945142]
  We investigate the possibility of applying Transformers for image matching and metric learning given pairs of images. We find that the Vision Transformer (ViT) and the vanilla Transformer with decoders are not adequate for image matching due to their lack of image-to-image attention. We propose a new simplified decoder, which drops the full attention implementation with the softmax weighting, keeping only the query-key similarity.
  arXiv  Detail & Related papers  (2021-05-30T05:38:33Z)
• Training Vision Transformers for Image Retrieval [32.09708181236154]
  We adopt vision transformers for generating image descriptors and train the resulting model with a metric learning objective. Our results show consistent and significant improvements of transformers over convolution-based approaches.
  arXiv  Detail & Related papers  (2021-02-10T18:56:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.